BenchmarkK2 Horizon 7B
- Institute of Foundation Models
- Veröffentlichung · 3. September 2026
- Offene Gewichte
- Reasoning
Intelligenz
Intelligence Index
#104 von 266- 21,522
GPT-6 Luna (Low) - 21,522A.X-K2
- 21,421
Qwen3.5 397B A17B (Non-reasoning) - 21,421
Nemotron 3.5 Bolt 74B-A9B - 20,821
GPT-5.6 Terra (Non-reasoning) - 20,621K2 Horizon 7B
- 20,420
Qwen3.5 Omni Plus - 20,420
DeepSeek V4 Pro 0813 (Non-reasoning) - 20,220
o3 - 20,220
Qwen3.8 27B (Non-reasoning)
Daten von Artificial Analysis- AA-Omniscience Accuracy12,8%#200
- Humanity's Last Exam18,2%#109
- Terminal-Bench 4.01%#77
- AA-LCR69,7%#108
- SciCode27,6%#127
- CritPt0,3%#117
- GPQA Diamond75,3%#91
- τ²-Bench Banking27,6%#35
K2 Horizon 7BMedian
Daten von Artificial AnalysisÄhnliche Modelle